© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 96060
    Prev
    Next
    INDEX
    Explanations

    specific entities associated with legal and educational qualifications

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    otty
    -0.06
    parate
    -0.06
    nod
    -0.06
     Au
    -0.06
     lasting
    -0.06
     McK
    -0.06
    )./
    -0.06
    StandardItem
    -0.06
    acket
    -0.06
    NST
    -0.06
    POSITIVE LOGITS
    tsky
    0.07
    iros
    0.07
    uner
    0.07
    atak
    0.07
    ä¸Ģ级
    0.07
    kara
    0.06
    omy
    0.06
    dge
    0.06
    Ø®ÛĮ
    0.06
     agr
    0.06
    Activations Density 0.010%

    No Known Activations